LIBERO and CALVIN fail multiple proposed diagnostics for shortcut solvability, statistical significance, overfitting, and data dependence, while a tiny 0.09B probe reaches near-SOTA on LIBERO.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
What Are We Actually Benchmarking in Robot Manipulation?
LIBERO and CALVIN fail multiple proposed diagnostics for shortcut solvability, statistical significance, overfitting, and data dependence, while a tiny 0.09B probe reaches near-SOTA on LIBERO.